# Classification on FashionMNIST (F1-Macro) Source: [Classification on FashionMNIST (F1-Macro)]() Collection index: [llms.txt]() Data updated: 2026-06-11T10:26:31.944Z Evaluation of classification performance on the FashionMNIST dataset, reporting the F1-Macro score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Classification | | Dataset (including any stated split) | FashionMNIST | | Metric | F1-Macro | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [F1-Macro](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1-Macro | Result date | Report paper | | --- | --- | --- | --- | | SiDyP | 90.84 | Not recorded | 6a2a4137d33dfb23e783944a | | SCE-Loss | 89.02 | Not recorded | 6a2a4137d33dfb23e783944a | | Original | 88.97 | Not recorded | 6a2a4137d33dfb23e783944a | | SELC | 88.77 | Not recorded | 6a2a4137d33dfb23e783944a | | CANOLA | 88.76 | Not recorded | 6a2a4137d33dfb23e783944a | | Canola | 88.76 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-R | 88.61 | Not recorded | 6a2a4137d33dfb23e783944a | | Canola | 88.57 | Not recorded | 6a2a4137d33dfb23e783944a | | SELC | 88.23 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-V | 88.05 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-V | 87.74 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-R | 87.51 | Not recorded | 6a2a4137d33dfb23e783944a | | DivideMix | 85.54 | Not recorded | 6a2a4137d33dfb23e783944a | | SiDyP | 84.77 | Not recorded | 6a2a4137d33dfb23e783944a | | SiDyP | 84.65 | Not recorded | 6a2a4137d33dfb23e783944a | | Original | 81.1 | Not recorded | 6a2a4137d33dfb23e783944a | | SiDyP | 78.89 | Not recorded | 6a2a4137d33dfb23e783944a | | CANOLA | 77.76 | Not recorded | 6a2a4137d33dfb23e783944a | | Canola | 77.76 | Not recorded | 6a2a4137d33dfb23e783944a | | DivideMix | 76.8 | Not recorded | 6a2a4137d33dfb23e783944a | | Co-Teaching | 75.88 | Not recorded | 6a2a4137d33dfb23e783944a | | SiDyP | 75.55 | Not recorded | 6a2a4137d33dfb23e783944a | | Co-Teaching | 74.81 | Not recorded | 6a2a4137d33dfb23e783944a | | SELC | 73.84 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-R | 73.34 | Not recorded | 6a2a4137d33dfb23e783944a | | Original | 72.83 | Not recorded | 6a2a4137d33dfb23e783944a | | Docta-V | 72.72 | Not recorded | 6a2a4137d33dfb23e783944a | | SCE-Loss | 72.55 | Not recorded | 6a2a4137d33dfb23e783944a | ### SiDyP F1-Macro: 90.84. Result ID: 6a2a8cdffbc373592c285e8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"Superv."}. This record does not assert independent reproduction. ### SCE-Loss F1-Macro: 89.02. Result ID: 6a2a8cdffbc373592c285e8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"Superv."}. This record does not assert independent reproduction. ### Original F1-Macro: 88.97. Result ID: 6a2a8cdffbc373592c285f4a. [Reporting paper]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### SELC F1-Macro: 88.77. Result ID: 6a2a8cdffbc373592c285f4d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### CANOLA F1-Macro: 88.76. Result ID: 6a2a8cdffbc373592c285e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"Superv."}. This record does not assert independent reproduction. ### Canola F1-Macro: 88.76. Result ID: 6a2a8cdffbc373592c285f4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### Docta-R F1-Macro: 88.61. Result ID: 6a2a8cdffbc373592c285f4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### Canola F1-Macro: 88.57. Result ID: 6a2a8cdffbc373592c285f55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### SELC F1-Macro: 88.23. Result ID: 6a2a8cdffbc373592c285f53. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### Docta-V F1-Macro: 88.05. Result ID: 6a2a8cdffbc373592c285f4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### Docta-V F1-Macro: 87.74. Result ID: 6a2a8cdffbc373592c285f51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### Docta-R F1-Macro: 87.51. Result ID: 6a2a8cdffbc373592c285f52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### DivideMix F1-Macro: 85.54. Result ID: 6a2a8cdffbc373592c285e8c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labelling technique":"Superv."}. This record does not assert independent reproduction. ### SiDyP F1-Macro: 84.77. Result ID: 6a2a8cdffbc373592c285f54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### SiDyP F1-Macro: 84.65. Result ID: 6a2a8cdffbc373592c285f4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"Superv."}. This record does not assert independent reproduction. ### Original F1-Macro: 81.1. Result ID: 6a2a8cdffbc373592c285f50. [Reporting paper]() Recorded evaluation configuration: {"Labeling technique":"Semi-Superv."}. This record does not assert independent reproduction. ### SiDyP F1-Macro: 78.89. Result ID: 6a2a8cdffbc373592c285f48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### CANOLA F1-Macro: 77.76. Result ID: 6a2a8cdffbc373592c285e89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"LLM"}. This record does not assert independent reproduction. ### Canola F1-Macro: 77.76. Result ID: 6a2a8cdffbc373592c285f49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### DivideMix F1-Macro: 76.8. Result ID: 6a2a8cdffbc373592c285e87. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labelling technique":"LLM"}. This record does not assert independent reproduction. ### Co-Teaching F1-Macro: 75.88. Result ID: 6a2a8cdffbc373592c285e8b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labelling technique":"Superv."}. This record does not assert independent reproduction. ### SiDyP F1-Macro: 75.55. Result ID: 6a2a8cdffbc373592c285e88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"LLM"}. This record does not assert independent reproduction. ### Co-Teaching F1-Macro: 74.81. Result ID: 6a2a8cdffbc373592c285e86. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labelling technique":"LLM"}. This record does not assert independent reproduction. ### SELC F1-Macro: 73.84. Result ID: 6a2a8cdffbc373592c285f47. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### Docta-R F1-Macro: 73.34. Result ID: 6a2a8cdffbc373592c285f46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### Original F1-Macro: 72.83. Result ID: 6a2a8cdffbc373592c285f44. [Reporting paper]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### Docta-V F1-Macro: 72.72. Result ID: 6a2a8cdffbc373592c285f45. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labeling technique":"LLM"}. This record does not assert independent reproduction. ### SCE-Loss F1-Macro: 72.55. Result ID: 6a2a8cdffbc373592c285e85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labelling technique":"LLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.